Neural Networks Optimized by Genetic Algorithms in Cosmology

TL;DR

This paper demonstrates that using genetic algorithms to optimize neural network hyperparameters in cosmology leads to more accurate and reliable models across various applications, outperforming traditional grid search methods.

Contribution

The study introduces a genetic algorithm-based approach for hyperparameter optimization in neural networks applied to cosmology, improving model performance and confidence.

Findings

Genetic algorithms significantly improve neural network architecture selection.

Optimized networks outperform grid search in cosmological tasks.

Enhanced model reliability in cosmology applications.

Abstract

The applications of artificial neural networks in the cosmological field have shone successfully during the past decade, this is due to their great ability of modeling large amounts of datasets and complex nonlinear functions. However, in some cases, their use still remains controversial because their ease of producing inaccurate results when the hyperparameters are not carefully selected. In this paper, to find the optimal combination of hyperparameters to artificial neural networks, we propose to take advantage of the genetic algorithms. As a proof of the concept, we analyze three different cosmological cases to test the performance of the architectures achieved with the genetic algorithms and compare them with the standard process, consisting of a grid with all possible configurations. First, we carry out a model-independent reconstruction of the distance modulus using a type Ia supernovae compilation. Second, the neural networks learn to infer the equation of state for the quintessence model, and finally with the data from a combined redshift catalog the neural networks predict the photometric redshift given six photometric bands (urgizy). We found that the genetic algorithms improve considerably the generation of the neural network architectures, which can ensure more confidence in their physical results because of the better performance in the metrics with respect to the grid method.